The process of Industry 4.0 is profoundly affecting the industrial structure of warehousing and intralogistics. However, it is unrealistic for many companies to build fully-automated warehouses by one-time investment due to the limitation of funds and/or restrictions on land registration, or, simply for some companies, Industry 5.0, which emphasises human participation, is more in line with their vision. Although existing solutions explicitly premise the coexistence of autonomous mobile robots (AMRs) and human workers, their main assumptions still include that humans must move carefully, and that the robot's current observations are able to match its priors about the work environment. Consequently, current robotic solutions usually have limited deployment space and high operation-maintenance costs. Therefore, there is a need to research and develop next-generation, more reliable and intelligent robotic navigation methods to enable large-scale deployment of affordable warehousing and intralogistics automation solutions. NavWare proposes to use data-driven deep learning methods to directly intervene in the AMR's navigation layers for fast and reliable local obstacle avoidance as well as generalizable global path planning, and ultimately generate safe worker-collaborative robot navigation. Compared with existing methods, robotic warehouse navigation based on NavWare may be less expensive to deploy and maintain, while the system performance may be better.

AIDD4H-V2 is a LabCom in the field of personalized medicine, initiated by the Oncodesign a biopharmaceutical company and the CIAD EA 7533 laboratory, specialized in Hybrid and explainable Artificial Intelligence. AIDD4H, for Artificial Intelligence in Drug Discovery for Health, focuses more specifically on the identification and validation of new therapeutic targets. This topic is a major innovation challenge for Oncodesign, giving it a competitive advantage in the development of new therapeutic molecules on behalf of its customers and for its pipeline. The Data Revolution in the healthcare sector is generating massive amounts of heterogeneous, temporal, multi-scale and multimodal data. To understand the complexity of cancers and serious diseases without known treatment, at the heart of Oncodesign's mission, and to allow the identification of new therapeutic targets, it is now necessary to integrate, annotate and enrich this data with the know-how in the domain of drug discovery chain. AIDD4H wishes, in combining the expertise of CIAD and Oncodesign’s DataScience Lab, to exploit the contribution of Artificial Intelligence by federating the approaches of modeling by data and modeling by knowledge and orient the associated research projects around the notions of Hybrid AI coupling Machine Learning and Knowledge Representation and Reasoning ( KRR) and Explainable AI integrating the knowledge of domain experts at the heart of the algorithm. These Explainable AIs combine connectionist AI approaches such as deep learning, neural networks ... and causal AIs based on the modeling of causal graphs of knowledge derived from the knowledge of experts. They help in the construction of explainable models, in the extraction of implicit / hidden knowledge, in the understanding of the complexity of biological entities and their interactions, in the discovery of new mechanisms of action and therefore ultimately in the identification of new therapeutic targets. AIDD4H, in addition to the complementary skills and know-how of the CIAD laboratory and Oncodesign, will also benefit from the data and knowledge generated during the PSPC project OncoSNIPE®, dedicated to the identification and characterization of patients resistant to anti-cancer treatments, and the PSPC IMODI®, dedicated to the characterization and development of predictive animal models in oncology. Explainable AI implemented by AIDD4H will make it possible to mitigate the “black box” nature of algorithms, bringing the necessary transparency to the decryption of hidden connections and complex contexts, to explain the choice of AI and help researchers and doctors in their research activities. To solve these issues, AIDD4H is structured around three work packages: WP-1 concerns the construction of a knowledge base by aggregating heterogeneous proprietary or public data sources. This axis will answer the question of the modeling and the acquisition of heterogeneous knowledge. WP-2 concerns the qualification of the truth and the value of this raw data to extract the implicit / hidden knowledge. This axis will use data mining, statistical and probabilistic analysis or machine learning approaches. WP-3 concerns the numerical and formal modeling of the reasoning involved in a know-how. This knowledge, resulting from interviews with domain experts, will be represented in a formal description logic model. Vocabulary and set of rules thus generated will allow experts to express their reasoning within developed AIs but also to AI the ability to explain its reasoning. This WP-3 will allow to combine connectionist and symbolic approaches to make these AI explicable. The innovation resulting from this WP-3 will be integrated into a target discovery platform developed in parallel by Oncodesign, which will allow by 2023 to accelerate the research and development phases of new molecules and to create new offerss that will ensure the sustainability of the LabCom.

The DALHAI project aims at developing compact all-optical Arithmetic and Logic Units (ALU) exploiting the spatial and spectral distributions of 2D confined plasmons modes in planar cavities tailored in ultrathin Au or Ag crystals. Yet, the optimization of the logic gate output contrast, the definition of the logic function reconfiguration schemes and the generalization of this concept towards complex ALU is a non-intuitive challenge. - - - DALHAI addresses the ALU design challenge with a four-stage strategy that relies, first, on the mode symmetry considerations that led to the successful numerical and experimental results obtained on the crystalline gold double hexagon (DH) devices. Second, evolutionary optimization will be implemented to efficiently survey the parameters space (shape, polarization, ...). Yet the discovery of complex ALU configurations will be limited by the intuitive starting points. Third, to overcome this limitation, DALHAI will develop powerful Hybrid Artificial Intelligence (HAI) tools and interface them with optical simulations and experimental data. Fourth, once trained, the HAI will propose device geometries and excitation protocols to solve the inverse design of complex reconfigurable ALUs. Nanofabrication, simulations, optical benchmarking, operation and reconfiguration of HAI-proposed ALUs will be performed. The experimental fabrication, optical testing and the numerical simulations of plasmonic ALUs will be performed by CEMES (CNRS, Toulouse) and ICB (CNRS, Dijon). CIAD (Univ. Bourgogne, Dijon) will develop the HAI in strong interaction with all partners. - - - DALHAI is structured in four work packages. WP1 is dedicated to management, dissemination and technological transfer actions. WP2 is the nano-optical backbone of the project in which the design, nanofabrication, optical testing, electro-plasmonic addressing and GDM simulations of simple 1st (DH-based) and 2nd (modified geometry) generation plasmonic ALU devices are implemented. WP3 is dedicated to the development of the connectionist and symbolic AI tools and their fusion into the Hybrid AI with continuous interactions with the numerical and experimental implementation of optimized plasmonic modal ALU (evolutionary optimization, 3rd generation). In WP4 the HAI will be deployed to propose structure and operation schemes of complex ALUs (4th generation) with associated experimental and numerical optical benchmarking, the HAI output will be qualified and specifications on the direct interfacing of the HAI with hardware and GDM routines will be established. - - - DALHAI targets two sets of science-to-technology breakthroughs with potential impact covered by specific dissemination and technology transfer actions. (1) The experimental nano-optical concepts of modal plasmonic gates and its generalization to ALU is an unprecedented holistic approach with which DALHAI ambitions to set a radically new and technologically relevant paradigm. DALHAI will disseminate its results at the crossroads of nano-optics and IT in high impact journals, in impactful conferences, in national and EU networks. (2) DALHAI will adapt HAI to assist the design of the complex ALU to step up in complexity, numbers of input/output and reconfigurability beyond intuitive design. DALHAI ambitions to enhance the innovation capacity by merging interdisciplinary fields and to establish a national and European leadership in HAI-reinforced nano-photonics. In this regards, DALHAI aims at a software maturity at TRL7. The machine learning part will be available for tests but the pioneering interdisciplinary approach of HAI in nanophotonics will be the subject of an invention declaration. We will establish an exploitation plan beyond the project duration with the technology transfer accelerator office SATT. Throughout the project a Wiki plus a public website will be maintained to share data but also as a promotional and educational tools towards the general public.

Rapidly evolving digital technologies such as the IoT, cloud and AI overrun classical industries, such as automotive, which have longer innovation and development cycles. The current trend of interconnecting cars with local infrastructure and cloud backends opens large potentials for data-driven applications, enhanced user experience, and new business models but also needs to consider privacy of the users inside the vehicle and others, just observed in the streets. This becomes especially critical with respect to GDPR. Goal of AUTOPSY is to create a better understanding of the data flows in automotive environments in the light of GDPR and create a privacy-aware system model for an automotive use-case to address various aspects of GDPR in specific technical designs. The technology of tainting will be applied to separate communication streams between the sensor and multiple parties accessing and processing the data with different privileges. AUTOPSY aims to design a dynamic and scalable end to end infrastructure that protects the data with lightweight privacy preserving techniques onboard the vehicle. Across the expertise of the different partners, the practical feasibility is demonstrated by modifying a resource constrained TCU with an implementation of the privacy-preserving techniques and evaluating its communication on the one hand, and the interaction with a cloud backend on the other. Bringing together one applied research partner and one automotive supplier from each country combines domain know-how and technological competencies to address the problem, develop new technologies and later enable new transnational services for customers. Transnational dissemination activities and the exchange of young researchers complement the research. To have privacy preserving techniques by design close to deployment in new cars in 2030 requires to start now and bring project results in the specification of the new automotive architectures in 2023-2024, which coincides with the earliest end of the project.